CN105184751A - Connected moving object detection method based on improved cluster - Google Patents

Abstract

A connected moving object detection method based on an improved cluster comprises the steps of converting two frames of continuous images into a gray level image; then adopting a C-cluster to segment the image, and obtaining a difference image by the image subtraction; scanning each pixel point in the difference image; when each pixel point is scanned, firstly determining whether the value of the pixel point is 1, if no, scanning the next pixel point continuously; if the value of the pixel point is 1, firstly defining the value of the pixel point as 1000, and then observing eight natural adjacent points of the pixel point, if the pixel values of the eight natural adjacent points are all not 1, ending the circulation, and detecting the next pixel point; if the pixel value of one of the eight natural adjacent point is 1, defining the pixel value of the point as 1000, and adding 1 in the value of a connection length; determining the connection length, if the connection length is less than 25, modifying the string of pixels as 0; if the connection length is greater than 25, modifying the pixel points as 1, and then comparing with an original image to obtain and detect an image of a moving object.

Description

A kind of connective Mobile object detection method based on improving cluster

Technical field

The present invention relates to technical field of image processing, providing a kind of connective Mobile object detection method based on improving cluster.

Background technology

In information age today, the development of society is advanced by leaps and bounds, and all trades and professions all be unable to do without information, especially image information.Image Information Processing is applied in every field widely as frontier science and technology interdisciplinary.Moving object detection is the result of the important topic in Image Information Processing, moving object detection, is usually the input picture of the senior aftertreatments such as next step target following, pattern-recognition, image understanding.In many occasions, such as the monitoring etc. of the magnitude of traffic flow, we are often interested in the object of motion.Therefore research is highly significant to the detection and tracking system of moving target sensitivity.In recent years, along with the fast development of multimedia technology and improving constantly of computing power, dynamic image pro cess technology is subject to the favor of people day by day, and achieves great successes, fields such as being widely used in traffic administration, military target is followed the tracks of, be biomedical.Target monitoring system, can replace operator on duty in warehouse with computing machine, transformer station, the important place such as bank monitor.Because still image treatment technology has certain limitation, and dynamic image comprises more information than still image, therefore, introduces motion monitoring necessary.

Moving object detection is the important topic in the fields such as machine vision, video information process and application vision research.In actual applications, utilizing moving object detection algorithm to carry out the result of Iamge Segmentation, is usually the input picture of the senior aftertreatments such as next step target following, pattern-recognition, image understanding.In actual life, a large amount of significant visual information is included among motion, and even the eyes of some animal are through evolving, and can only see the object of motion.Although human vision can see that motion can see static object again, but in many occasions, such as the security personnel of the monitoring of the magnitude of traffic flow, important place, aviation and the guidance of military spacecraft, the automatic Pilot of automobile or auxiliary driving etc., we are often interested in the object of motion.Therefore research is highly significant to the detection and tracking system of moving target sensitivity.In addition, the research object of moving target is image sequence, and it is easy to want comparison single-frame images to do static analysis to the study general of image sequence.

Summary of the invention

The object of the present invention is to provide and a kind of moving object in the image collected to be identified, overcome traditional images and just carry out difference without cluster, there is the problem that noise is large.

Based on the connective Mobile object detection method improving cluster, it is characterized in that comprising:

Step 1, colored for continuous print two frame jpg image is converted into gray level image;

Step 2: the value choosing arbitrarily c different size from 0 to 255 becomes the central value of c class as Iamge Segmentation, namely adopts the integer initialization of 0 to 255 value, make k=0;

Step 3: by the gray-scale value g (x, y) of diverse location pixels all in image (x=1,2 ..., M, y=1,2 ..., N) and a certain class given in c class is divided one by one by minimal distance principle, namely

If $d_{(x,y)l}^{\left(k\right)}=\underset{j}{\min }\left\{d_{(x,y)j}^{\left(k\right)}\right\},x=1,2,...,M,y=1,2,...,N,$ Exist a l ∈ 1,2 ..., c};

Then judge $g(x,y)\∈{\mathrm{\ω}}_l^{(k+1)},{\mathrm{\ω}}_l^{(k+1)}(l=1,2,...,c)$ For cluster;

In formula represent g (x, y) and center distance, superscript represents iterations, so produce new cluster ${\mathrm{\ω}}_j^{(k+1)}(j=\mathrm{1,2},...,c);$

Step 4: calculate all kinds of centers after reclassifying

$z_j^{(k+1)}=\frac{1}{n_j^{(k+1)}}\underset{g(x,y)\∈{\mathrm{\ω}}_j^{(k+1)}}{\Σ}g(x,y),j=1,2,...,c$

In formula for the number of contained pattern in class;

If step 5 then carry out step 6; Otherwise k=k+1, goes to step 3;

Step 6, the difference image of two frame gray level images is obtained to the image subtraction that step 5 exports;

Step 7, each pixel in difference image to be scanned;

Step 8, when often scanning a pixel, first judge whether the value of this pixel is 1, if be not 1, then scan next pixel; If be 1, carry out step 9;

Step 9, first the value of this pixel to be composed be 1000, then by 8 Natural neighbors of nested this pixel of circulation observation, if do not have in those 8 Natural neighbors pixel value be 1 point, just terminate this circulation, then detect next pixel; If the pixel value having some point at these 8 Natural neighbors is 1, then the pixel value of these points being composed is 1000, and connecting length is added 1, more so operates its neighbor pixel;

Step 10, judge connecting length, if connecting length is less than 25, then can think the point in background, then the value of this crossview vegetarian refreshments being changeed back by 1000 is 0; If connecting length is greater than 25, then can think moving object, then the value of this crossview vegetarian refreshments being changeed back by 1000 is 1, then compares with former figure, draws the image detecting moving target.

The technical solution used in the present invention is as follows:

The present invention first carries out cluster to image, then carries out difference, effectively reduces the noise of image like this.

Embodiment

All features disclosed in this instructions, or the step in disclosed all methods or process, except mutually exclusive feature and/or step, all can combine by any way.

Based on the connective Mobile object detection method improving cluster, it is characterized in that comprising:

Step 1, colored for continuous print two frame jpg image is converted into gray level image;

Step 2: the value choosing arbitrarily c different size from 0 to 255 becomes the central value of c class as Iamge Segmentation, namely adopts the integer initialization of 0 to 255 value, make k=0;

Step 3: by the gray-scale value g (x, y) of diverse location pixels all in image (x=1,2 ..., M, y=1,2 ..., N) and a certain class given in c class is divided one by one by minimal distance principle, namely

If x=1,2 ..., M, y=1,2 ..., N, exist a l ∈ 1,2 ..., c};

Then judge $g(x,y)\∈{\mathrm{\ω}}_l^{(k+1)},{\mathrm{\ω}}_l^{(k+1)},(l=1,2,...,c)$ For cluster;

In formula represent g (x, y) and center distance, superscript represents iterations, so produce new cluster ${\mathrm{\ω}}_j^{(k+1)},(j=1,2,...,c);$

Step 4: calculate all kinds of centers after reclassifying

$z_j^{(k+1)}=\frac{1}{n_j^{(k+1)}}\underset{g(x,y)\∈{\mathrm{\ω}}_j^{(k+1)}}{\Σ}g(x,y),j=1,2,...,c$

In formula for the number of contained pattern in class;

If step 5 then carry out step 6; Otherwise k=k+1, goes to step 3;

Step 6, the difference image of two frame gray level images is obtained to the image subtraction that step 5 exports;

Step 7, each pixel in difference image to be scanned;

Step 8, when often scanning a pixel, first judge whether the value of this pixel is 1, if be not 1, then scan next pixel; If be 1, carry out step 9;

Step 9, first the value of this pixel to be composed be 1000, then by 8 Natural neighbors of nested this pixel of circulation observation, if do not have in those 8 Natural neighbors pixel value be 1 point, just terminate this circulation, then detect next pixel; If the pixel value having some point at these 8 Natural neighbors is 1, then the pixel value of these points being composed is 1000, and connecting length is added 1, more so operates its neighbor pixel;

Step 10, judge connecting length, if connecting length is less than 25, then can think the point in background, then the value of this crossview vegetarian refreshments being changeed back by 1000 is 0; If connecting length is greater than 25, then can think moving object, then the value of this crossview vegetarian refreshments being changeed back by 1000 is 1, then compares with former figure, draws the image detecting moving target.

Claims (1)

1., based on the connective Mobile object detection method improving cluster, it is characterized in that comprising:

Step 1, colored for continuous print two frame jpg image is converted into gray level image;

Step 2: the value choosing arbitrarily c different size from 0 to 255 becomes the central value of c class as Iamge Segmentation, namely adopts the integer initialization of 0 to 255 value, make k=0;

Step 3: by the gray-scale value g (x, y) of diverse location pixels all in image (x=1,2 ..., M, y=1,2 ..., N) and a certain class given in c class is divided one by one by minimal distance principle, namely

If $d_{(x,y)l}^{\left(k\right)}=\underset{j}{\min }\left\{d_{(x,y)j}^{\left(k\right)}\right\},x=1,2,...,M,y=1,2,...,N,$ Exist a l ∈ 1,2 ..., c};

Then judge $g(x,y)\∈{\mathrm{\ω}}_l^{(k+1)},{\mathrm{\ω}}_l^{(k+1)}(l=1,2,...,c)$ For cluster;

In formula represent g (x, y) and center distance, superscript represents iterations, so produce new cluster ${\mathrm{\ω}}_j^{(k+1)}(j=1,2,...,c):$

Step 4: calculate all kinds of centers after reclassifying

$z_j^{(k+1)}=\frac{1}{n_j^{(k+1)}}\underset{g(x,y)\∈{\mathrm{\ω}}_j^{(k+1)}}{\Σ}g(x,y),j=1,2,...,c$

In formula for the number of contained pattern in class;

If step 5 then carry out step 6; Otherwise k=k+1, goes to step 3;

Step 6, the difference image of two frame gray level images is obtained to the image subtraction that step 5 exports;

Step 7, each pixel in difference image to be scanned;

Step 8, when often scanning a pixel, first judge whether the value of this pixel is 1, if be not 1, then scan next pixel; If be 1, carry out step 9;

Step 9, first the value of this pixel to be composed be 1000, then by 8 Natural neighbors of nested this pixel of circulation observation, if do not have in those 8 Natural neighbors pixel value be 1 point, just terminate this circulation, then detect next pixel; If the pixel value having some point at these 8 Natural neighbors is 1, then the pixel value of these points being composed is 1000, and connecting length is added 1, more so operates its neighbor pixel;

Step 10, judge connecting length, if connecting length is less than 25, then can think the point in background, then the value of this crossview vegetarian refreshments being changeed back by 1000 is 0; If connecting length is greater than 25, then can think moving object, then the value of this crossview vegetarian refreshments being changeed back by 1000 is 1, then compares with former figure, draws the image detecting moving target.